Department of Biomedical Engineering & Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.
Department of Anatomy & Neurosciences, MS Center Amsterdam, Amsterdam Neuroscience, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.
Phys Med Biol. 2022 Jun 8;67(12). doi: 10.1088/1361-6560/ac6cc2.
Machine Learning methods can learn how to reconstruct magnetic resonance images (MRI) and thereby accelerate acquisition, which is of paramount importance to the clinical workflow. Physics-informed networks incorporate the forward model of accelerated MRI reconstruction in the learning process. With increasing network complexity, robustness is not ensured when reconstructing data unseen during training. We aim to embed data consistency (DC) in deep networks while balancing the degree of network complexity. While doing so, we will assess whether either explicit or implicit enforcement of DC in varying network architectures is preferred to optimize performance.We propose a scheme called Cascades of Independently Recurrent Inference Machines (CIRIM) to assess DC through unrolled optimization. Herein we assess DC both implicitly by gradient descent and explicitly by a designed term. Extensive comparison of the CIRIM to compressed sensing as well as other Machine Learning methods is performed: the End-to-End Variational Network (E2EVN), CascadeNet, KIKINet, LPDNet, RIM, IRIM, and UNet. Models were trained and evaluated on T-weighted and FLAIR contrast brain data, and T-weighted knee data. Both 1D and 2D undersampling patterns were evaluated. Robustness was tested by reconstructing 7.5× prospectively undersampled 3D FLAIR MRI data of multiple sclerosis (MS) patients with white matter lesions.The CIRIM performed best when implicitly enforcing DC, while the E2EVN required an explicit DC formulation. Through its cascades, the CIRIM was able to score higher on structural similarity and PSNR compared to other methods, in particular under heterogeneous imaging conditions. In reconstructing MS patient data, prospectively acquired with a sampling pattern unseen during model training, the CIRIM maintained lesion contrast while efficiently denoising the images.The CIRIM showed highly promising generalization capabilities maintaining a very fair trade-off between reconstructed image quality and fast reconstruction times, which is crucial in the clinical workflow.
机器学习方法可以学习如何重建磁共振图像 (MRI)，从而加速采集，这对临床工作流程至关重要。物理信息网络将加速 MRI 重建的正向模型纳入学习过程中。随着网络复杂性的增加，在训练中未见过的数据重建时，其稳健性无法得到保证。我们的目标是在深度网络中嵌入数据一致性 (DC)，同时平衡网络复杂性的程度。在这样做的过程中，我们将评估在不同的网络架构中是优先显式还是隐式执行 DC，以优化性能。我们提出了一种称为独立递归推理机级联 (CIRIM) 的方案，通过展开优化来评估 DC。在这里，我们通过梯度下降隐式地评估 DC，并通过设计的项显式地评估 DC。对 CIRIM 与压缩感知以及其他机器学习方法进行了广泛的比较：端到端变分网络 (E2EVN)、CascadeNet、KIKINet、LPDNet、RIM、IRIM 和 UNet。在 T 加权和 FLAIR 对比度脑数据以及 T 加权膝关节数据上对模型进行了训练和评估。评估了 1D 和 2D 欠采样模式。通过重建多发性硬化症 (MS)患者具有白质病变的 7.5×前瞻性欠采样 3D FLAIR MRI 数据来测试稳健性。当隐式执行 DC 时，CIRIM 表现最佳，而 E2EVN 需要显式 DC 公式。通过级联，CIRIM 在结构相似性和 PSNR 方面的得分高于其他方法，特别是在异构成像条件下。在重建 MS 患者数据时，使用模型训练期间未见过的采样模式进行前瞻性采集，CIRIM 保持了病变对比度，同时有效地对图像进行去噪。CIRIM 表现出非常有前途的泛化能力，在重建图像质量和快速重建时间之间保持了非常公平的折衷，这在临床工作流程中至关重要。
